agentleFS
XPOZpublicXPOZpublic/geo-seo-agent/llms.txt

geo-seo-agent

llms.txt0 starsChanged 3 months agoMITView on GitHub

Open, agent-operated GEO (Generative Engine Optimization) program manager for tech companies, built by the team at xpoz.ai. Operated through Claude Code: it discovers the prompts buyers ask AI engines, measures search-grounded visibility in Claude, ChatGPT, and Gemini answers on a fixed prompt panel, diagnoses content gaps with evidence, produces content (site and documentation) and third-party presence (review sites, GitHub, marketplaces, AI-ecosystem integrations), and runs retrospectives. Humans approve at every gate.

The file

Files
llms.txt
# geo-seo-agent

> Open, agent-operated GEO (Generative Engine Optimization) program manager for tech companies, built by the team at xpoz.ai. Operated through Claude Code: it discovers the prompts buyers ask AI engines, measures search-grounded visibility in Claude, ChatGPT, and Gemini answers on a fixed prompt panel, diagnoses content gaps with evidence, produces content (site and documentation) and third-party presence (review sites, GitHub, marketplaces, AI-ecosystem integrations), and runs retrospectives. Humans approve at every gate.

## Docs

- [README](README.md): what it is, what you need, quickstart, layout
- [CLAUDE.md](CLAUDE.md): agent orientation: the operating loop, scripts, skills, data locations, ground rules
- [GEO strategy](strategy/geo-strategy.md): mission, operating principles, KPIs
- [GEO writing principles](strategy/geo-writing-principles.md): evidence-based rules for AI-citable content, with sources
- [Channel playbook](strategy/channel-playbook.md): the surfaces AI engines assemble answers from and how evidence steers effort

## Examples

- [Sample visibility summary](examples/sample-visibility-summary.md): what one sensor run produces (fabricated data)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.